Saarbrücken, Univ., Diss., 2004.

Στην παρούσα εργασία διερευνήθηκαν οι προσδιοριστικοί παράγοντες της επίδοσης των αποφοίτων της τριτοβάθμιας εκπαίδευσης (πανεπιστημιακής) στην Ελλάδα. Για τους σκοπούς της ανάλυσης χρησιμοποιήθηκαν στοιχεία διαστρωματικών χρονοσειρών σε επίπεδο πανεπιστημιακού τμήματος για την περίοδο 2001-2007 (Ελληνική Στατιστική Αρχή, ΕΛ.ΣΤΑΤ). Ως δείκτης επίδοσης χρησιμοποιήθηκε το ποσοστό των αποφοίτων με βαθμό πτυχίου “άριστα”, “λίαν καλώς” και “καλώς” και ως εκ τούτου το οικονομετρικό υπόδειγμα που εφαρμόστηκε είναι τύπου fractional logit. Βασιζόμενοι στην σχετική διεθνή βιβλιογραφία, ως επεξηγηματικές μεταβλητές χρησιμοποιήθηκαν πληροφορίες ανά πανεπιστημιακό τμήμα για την βάση εισαγωγής, το αντικείμενο σπουδών του τμήματος, την παλαιότητά του, το ποσοστό των φοιτητών που δηλώνουν ως τόπο κατοικίας την ίδια πόλη με αυτή της σχολής καθώς και την αναλογία φοιτητών ανά μέλη ΔΕΠ. Με βάση τα αποτελέσματα βρέθηκε ότι το αντικείμενο σπουδών και η παλαιότητα του πανεπιστημιακού τμήματος αποτελούν τους βασικούς προσδιοριστικούς παράγοντες της επίδοσης των αποφοίτων στα ελληνικά πανεπιστήμια. Να σημειωθεί ότι τα παραπάνω αποτελέσματα βρίσκονται σε συμφωνία με αυτά της σχετικής βιβλιογραφίας. / --

Στην παρούσα εργασία διερευνήθηκαν οι προσδιοριστικοί παράγοντες του βαθμού αποφοίτησης των πτυχιούχων των τμημάτων Οικονομικής Επιστήμης στην Ελλάδα. Τα στοιχεία που χρησιμοποιήθηκαν για τους σκοπούς της ανάλυσης προέρχονται από τα δευτερογενή δημοσιευμένα στοιχεία της Ελληνικής Στατιστικής Αρχής και αφορούν απόφοιτους σε επίπεδο πανεπιστημιακού τμήματος για τα έτη 2001-2007. Ως δείκτες επίδοσης χρησιμοποιήθηκε το ποσοστό των αποφοίτων με βαθμό πτυχίου " Άριστα", "Λίαν Καλώς" και "Καλώς". Στην εμπειρική ανάλυση χρησιμοποιήθηκαν υποδείγματα τύπου "fractional logit" επειδή η προς εξέταση μεταβλητή εμφανίζεται σε ποσοστά. Με βάση προγενέστερες μελέτες, κυρίως σε διεθνές επίπεδο, ως ερμηνευτικές μεταβλητές χρησιμοποιήσαμε το βαθμό εισαγωγής στα τμήματα Οικονομικής Επιστήμης που εξετάζουμε, την παλαιότητα των τμημάτων, το ποσοστό των φοιτητών που φοιτούν στον τόπο μόνιμης κατοικίας τους, την πληθυσμιακή πυκνότητα των νομών όπου είναι εγκατεστημένα τα τμήματα, τους δείκτες ερευνητικής επάρκειας των μελών ΔΕΠ και την αναλογία μελών ΔΕΠ σε κάθε βαθμίδα προς το σύνολό τους. Ακόμα συμπεριλάβαμε το έτος αποφοίτησης, αλλά και την αναλογία εγγεγραμμένων φοιτητών στα πλαίσια του κανονικού ορίου φοίτησης (συνολικά και μόνο τις γυναίκες) και φοιτητών πέραν του κανονικού ορίου φοίτησης προς το σύνολο των εγγεγραμμένων φοιτητών αντίστοιχα. Σε γενικές γραμμές σύμφωνα με τα ευρήματα της παρούσας ανάλυσης ο βαθμός αποφοίτησης των πτυχιούχων των τμημάτων Οικονομικής Επιστήμης δεν διαμορφώνεται με τον ίδιο τρόπο αλλά φαίνεται να διαφέρει συστηματικά μεταξύ των τμημάτων. Ειδικότερα, ο βαθμός εισαγωγής αποτελεί βασικό προσδιοριστικό παράγοντα του βαθμού επίδοσης, αποτέλεσμα που συμβαδίζει με τη διεθνή εμπειρική ένδειξη. Περαιτέρω, εμφανίζεται σημαντική η αναλογία μελών ΔΕΠ σε κάθε βαθμίδα προς το σύνολό τους αλλά και το έτος αποφοίτησης. / In this study we investigated the determinants of degree performance of graduates of Economic Departments in Greece.

Correlated ordinal data typically arises from multiple measurements on a collection of subjects. Motivated by an application in credit risk, where multiple credit rating agencies assess the creditworthiness of a firm on an ordinal scale, we consider multivariate ordinal regression models with a latent variable specification and correlated error terms. Two different link functions are employed, by assuming a multivariate normal and a multivariate logistic distribution for the latent variables underlying the ordinal outcomes. Composite likelihood methods, more specifically the pairwise and tripletwise likelihood approach, are applied for estimating the model parameters. Using simulated data sets with varying number of subjects, we investigate the performance of the pairwise likelihood estimates and find them to be robust for both link functions and reasonable sample size. The empirical application consists of an analysis of corporate credit ratings from the big three credit rating agencies (Standard & Poor's, Moody's and Fitch). Firm-level and stock price data for publicly traded US firms as well as an unbalanced panel of issuer credit ratings are collected and analyzed to illustrate the proposed framework.

Submitted by Cristiane Oliveira (cristiane.oliveira@fgv.br) on 2011-06-02T14:19:07Z No. of bitstreams: 1 68060200615.pdf: 1957316 bytes, checksum: 67eec7a2cc1a056e7bb0f0db8532a1d9 (MD5) / Approved for entry into archive by Suzinei Teles Garcia Garcia(suzinei.garcia@fgv.br) on 2011-06-02T14:44:39Z (GMT) No. of bitstreams: 1 68060200615.pdf: 1957316 bytes, checksum: 67eec7a2cc1a056e7bb0f0db8532a1d9 (MD5) / Approved for entry into archive by Suzinei Teles Garcia Garcia(suzinei.garcia@fgv.br) on 2011-06-02T14:45:56Z (GMT) No. of bitstreams: 1 68060200615.pdf: 1957316 bytes, checksum: 67eec7a2cc1a056e7bb0f0db8532a1d9 (MD5) / Made available in DSpace on 2011-06-02T15:00:17Z (GMT). No. of bitstreams: 1 68060200615.pdf: 1957316 bytes, checksum: 67eec7a2cc1a056e7bb0f0db8532a1d9 (MD5) Previous issue date: 2010-12-14 / Após o surgimento e a expansão exponencial, a internet evoluiu para uma tecnologia que extrapolou os contornos acadêmicos em que foi criada, desenvolvendo diversas e simultâneas vocações, entre elas, fonte de educação e lazer, armazenamento de informações, rede de computadores, meio de comunicação individual e veículo de mídia de massa. É esta vocação, de veículo de mídia, que provocou o interesse pela pesquisa objeto desta dissertação. A entrada da internet no ambiente de mídia tem renovado o interesse na questão do consumo de mídia. Particularmente, a crescente popularidade como novo meio de comunicação resultou em mudanças nos usos dos meios tradicionais, como teorizado na Teoria do Nicho aplicada à indústria de mídia. O declínio da audiência das grandes redes de TV aberta mostra como o setor vem reagindo à concorrência de novos canais, à emergência de novas plataformas de acesso à programação televisiva e à mudança nos hábitos de consumo de mídia. Esta investigação faz uma revisão da literatura e compara o panorama internacional e especialmente a situação do Brasil, onde as principais emissoras de sinal aberto tentam resistir ao processo de fragmentação do público que se registra mundialmente. Para melhor compreender o que significam tais mudanças, é primordial entender quais as variáveis relevantes no universo dos veículos de mídia. A principal delas é a audiência, que representa o número de pessoas que acessam, veem, leem, ouvem ou consomem determinado meio de comunicação em determinado espaço de tempo. O objetivo deste estudo foi desenvolver um modelo preditivo sobre o tempo despendido pelas pessoas na internet, a partir de informações sociodemográficas e do comportamento dessas pessoas enquanto audiência dos meios de comunicação tradicionais, particularmente a televisão. Como os dados secundários analisados apresentam respostas em categorias ordinais, foi escolhido a regressão logística ordinal como o modelo de probabilidades para realizar esse estudo.

This master’s thesis project consists of two parts. Part I of the project compares modeling of historical resource production and forecasting of future production trends using the logit/probit transform advocated by Rutledge (2011) with conventional Hubbert curve fitting, using global coal production as a case study. The conventional Hubbert/Gaussian method fits a curve to historical production data whereas a logit/probit transform uses a linear fit to a subset of transformed production data. Within the errors and limitations inherent in this type of statistical modeling, these methods provide comparable results. That is, despite that apparent goodness-of-fit achievable using the Logit/Probit methodology, neither approach provides a significant advantage over the other in either explaining the observed data or in making future projections. For mature production regions, those that have already substantially passed peak production, results obtained by either method are closely comparable and reasonable, and estimates of ultimately recoverable resources obtained by either method are consistent with geologically estimated reserves. In contrast, for immature regions, estimates of ultimately recoverable resources generated by either of these alternative methods are unstable and thus, need to be used with caution. Although the logit/probit transform generates high quality-of-fit correspondence with historical production data, this approach provides no new information compared to conventional Gaussian or Hubbert-type models and may have the effect of masking the noise and/or instability in the data and the derived fits. In particular, production forecasts for immature or marginally mature production systems based on either method need to be regarded with considerable caution. Part II of the project investigates the utility of a novel alternative method for multicyclic Hubbert modeling tentatively termed “cycle-jumping” wherein overlap of multiple cycles is limited. The model is designed in a way that each cycle is described by the same three parameters as conventional multicyclic Hubbert model and every two cycles are connected with a transition width. Transition width indicates the shift from one cycle to the next and is described as weighted coaddition of neighboring two cycles. It is determined by three parameters: transition year, transition width, and γ parameter for weighting. The cycle-jumping method provides superior model compared to the conventional multicyclic Hubbert model and reflects historical production behavior more reasonably and practically, by better modeling of the effects of technological transitions and socioeconomic factors that affect historical resource production behavior by explicitly considering the form of the transitions between production cycles.

In this paper we study data on discrete labor market transitions from Austria. In particular, we follow the careers of workers who experience a job displacement due to plant closure and observe - over a period of 40 quarters - whether these workers manage to return to a steady career path. To analyse these discrete-valued panel data, we apply a new method of Bayesian Markov chain clustering analysis based on inhomogeneous first order Markov transition processes with time-varying transition matrices. In addition, a mixtureof- experts approach allows us to model the probability of belonging to a certain cluster as depending on a set of covariates via a multinomial logit model. Our cluster analysis identifies five career patterns after plant closure and reveals that some workers cope quite easily with a job loss whereas others suffer large losses over extended periods of time.

Promover a segurança viária no entorno escolar é uma estratégia que contribui para que sejam construídas cidades seguras, saudáveis e sustentáveis. Nesse sentido, este estudo é dedicado a identificar a influência das características da estrutura urbana na frequência e na severidade dos acidentes no entorno de escolas de educação básica de Porto Alegre. A análise da frequência e da severidade de acidentes foi conduzida através da estimação de modelos econométricos: binomial negativo e logit ordenado, respectivamente. Para esses, foram calculados os efeitos marginais, permitindo a observação da magnitude dos impactos das variáveis explicativas sobre as variáveis dependentes. As variáveis dependentes frequência e severidade foram extraídas dos acidentes registrados em Porto Alegre entre 2012 e 2014. Foram incluídas, simultaneamente, variáveis da estrutura urbana, das escolas, socioeconômicas e dos acidentes (para a severidade). A partir do geoprocessamento dos dados existentes, os entornos escolares puderam ser caracterizados para três diferentes áreas circulares de análise (buffer ring) de raios de 100, 150 e 200 metros, permitindo a comparação do uso das diferentes áreas. O conjunto de estimativas indica que áreas menores produzem modelos de melhor desempenho para ambas as técnicas empregadas. No entanto, áreas maiores permitem a análise de maior quantidade de variáveis relativas à estrutura urbana. Essa relação sugere os benefícios da escolha a partir do trade-off entre ajuste do modelo e sua capacidade de propiciar análises de variáveis. Foi identificado que a frequência e a severidade de acidentes podem estar relacionadas a uma única variável explicativa de formas opostas – a partir de sinais contrários. Essa diferença de resultados para frequência e severidade de acidentes indica que há maiores benefícios em analisá-las em conjunto. Identificou-se ainda que existem benefícios para a segurança viária em áreas de estrutura urbana com quarteirões menores e maior quantidade de interseções de quatro vias, em frequência e severidade, respectivamente. Já as áreas mais arborizadas tendem a apresentar acidentes de menor severidade nos casos de usuários de modos ativos. / Fostering road safety nearby schools is a strategy that contributes to build safe, healthy and sustainable cities. The aim of this study is to identify the influence of the built environment characteristics in the frequency and severity of accidents nearby elementary and secondary schools in Porto Alegre. The frequency and severity of the accidents were analyzed using econometric models: negative binomial and ordered logit, respectively. The evaluation of their marginal effects allowed the magnitude of the impact caused by the explanatory variable on the dependent variables to be observed. The measured variables frequency and severity were extracted from accidents registered in Porto Alegre from 2012 and 2014. Built environment, socioeconomic and school variables were also included, as well as accident data (for severity). Data geoprocessing allowed school surroundings to be characterized for three different buffer rings, measuring 100, 150 and 200 meters of radius. Thereby it was possible to compare the inclusion of different areas in the study. The estimations indicates that models based on smaller areas have better performances for both employed techniques, whereas larger areas allow the study of a bigger quantity of urban infrastructure variables. That indicates the benefits of choosing based on a trade-off between model adjustment and capacity to engender the analysis of variables. It was shown that frequency and severity of accidents could be related to a single explanatory variable in opposite ways – based on contrary signs. This difference in the results found for frequency and severity indicates that there are more benefits when analyzing them together. Moreover, there are benefits for road safety in areas where the city blocks are shorter and where there are more four-way intersections, in frequency and severity of accidents, respectively. Also, areas of more important afforestation tend to decrease the severity of accidents involving users of active modes.

Magíster en Gestión de Operaciones. Ingeniero Civil Matemático / En esta tesis se estudia el desarrollo de cuestionarios eficientes para el modelo de elección discreta de eliminación por aspectos. El estudio está motivado por la teoría de error desarrollada por Kohli, Jedidi y Montoya para este modelo, donde se calculan de forma explícita las probabilidades de elección de dicho modelo, y por ser más general que otros modelos más populares, como el logit o el ranking. A diferencia de los modelos clásicos, este modelo no cabe dentro de los llamados modelos compensatorios (que suponen que todas las características relevantes son consideradas en el proceso de elección) por lo que las técnicas ya existentes o bien deben ser adaptadas o bien descartadas por otras nuevas. El objetivo de esta tesis es resolver el problema de obtener cuestionarios acordes al modelo de eliminación por aspectos que permitan recuperar los parámetros intrínsecos de dicho modelo de manera eficiente. Se modela el problema como uno de optimización en dos niveles, cuya resolución entrega cuestionarios con las características antes mencionadas. Se provee de un algoritmo computacional para buscar dichos cuestionarios para el caso de dos y tres alternativas por pregunta, además de una cota teórica en el número de preguntas. Se obtienen resultados con respecto a la optimalidad local (D-eficiencia) de los cuestionarios. Para los casos de dos y tres alternativas por conjunto de elección, el resultado es que los cuestionarios arrojados por el programa son más eficientes a la hora de estimar los parámetros, pero no lo son si el criterio considerado es la distancia del parámetro estimado al real. Además, se describen los cuestionarios mediante características que son relevantes en los modelos de regresión lineal, y se analiza qué tanto varían dichas características con respecto a los cuestionarios clásicos. Como resultado secundario se obtienen, para los casos antes mencionados, cotas en el número de preguntas máximas necesarias para construir un cuestionario. Estas cotas son en cierto sentido restrictivas, pero necesarias a la hora de resolver el problema de optimización. Un tercer resultado que se obtiene tiene que ver con que los tiempos de resolución del algoritmo son aceptables en las pruebas realizadas, pero el problema no es escalable para aplicar esto en instancias más grandes. Se concluye que el procedimiento antes descrito permite obtener diseños para el modelo de eliminación por aspectos que son más eficientes que los modelos compensatorios clásicos para poder estimar los parámetros. Esto sugiere usar el modelo de eliminación por aspectos cuando existe evidencia que apoye el hecho de que los respondientes no realizan el ejercicio de considerar todas las características. / Este trabajo ha sido parcialmente financiado por Fondecyt Regular 1151395

Orientador: Alexandre Sartoris Neto / Banca: Luciana Togeiro / Banca: Marislei Nishijima / Resumo: A Educação Superior pode ser considerada uma ferramenta que possibilita ao indivíduo, através do investimento em seu Capital humano, ampliação de sua capacidade produtiva, maiores salários, proporcionando menor iniqüidade na distribuição de renda entre os indivíduos. O objetivo deste trabalho é traçar um perfil sócio-econômico do recém formado no ensino superior brasileiro com base em dados do Exame Nacional do Desempenho dos Estudantes (ENADE). Como se sabe, a escolha do curso superior no Brasil tem forte influência de fatores sociais e econômicos. Para estimar probabilidades com que um graduado seja de determinado curso, dado seu perfil, um modelo logit multinomial foi estimado. Conclui-se que quando a expectativa em relação ao curso é de ganhos futuros, homens brancos, negros e mulatos tendem a escolher cursos de exatas e engenharias. Em contrapartida, os cursos de humanas, em sua maioria, são demandados por mulheres brancas, negras e mulatas. Mesmo assim, há mulheres brancas, em certas regiões como Sudeste e Sul, que tem preferência por curso de engenharias e exatas / Abstract: Higher education can be considered a tool that enables an individual, through investment in human capital, expanding his or her production abilities, higher wages, providing less unequal distribution of income among individuals.This work aims to build a profile of the Brazilian college graduated based on data from ENADE (Student Performance National Exam). As fairly known, college career choice in Brazil is strongly affected by social and economic factors. In order to estimate the probability of choosing a career, given the student profile, a multinomial logit model will be estimated. It is possible to conclude that when the expectation is over the course of future earnings, white males, blacks and mulattoes tend choose the exact and engineering courses. In contrast, the humanities courses, mostly, are demanded by white, black and mulatto. Still, there are white women in certain regions such as Southeast and South, which has a preference for engineering courses and exact / Mestre